| Presentation | 2022-03-11 A Study on Bayesian Spatial and Temporal Modeling Approach to Environmental Feature Inference Using Driving Signals From Vehicles Yukio Ogawa, Go Hasegawa, Masayuki Murata, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Connected vehicles become an ambient sensing platform, as a number of different signals that they record become available for analyzing urban living environments. Although such signals can inform environmental state like fine-grained road and weather conditions, they include false positives and negatives. We therefore propose a two-step Bayesian modeling approach combining spatial Markov random fields and temporal Bayesian network for inferring the binary state of environment using such uncertain data. Our approach first minimize the randomness of data exploiting the spatial relationship among data. It then recursively infers the likelihood of binary state of environment in the near future by using the temporal dependency among them. Through computer simulations using the vehicular trace of a city-wide area, we demonstrate that our approach infers the probability of recurrent road traffic congestion occurring every few minutes up to about 80%. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | connected vehicles / environmental sensing / spatial-temporal / Bayesian modeling / uncertain data |
| Paper # | IN2021-43 |
| Date of Issue | 2022-03-03 (IN) |
| Conference Information | |
| Committee | NS / IN |
|---|---|
| Conference Date | 2022/3/10(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | General |
| Chair | Akihiro Nakao(Univ. of Tokyo) / Kenji Ishida(Hiroshima City Univ.) |
| Vice Chair | Tetsuya Oishi(NTT) / Kunio Hato(Internet Multifeed) |
| Secretary | Tetsuya Oishi(NTT) / Kunio Hato(Chuo Univ.) |
| Assistant | Kotaro Mihara(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Network Systems / Technical Committee on Information Networks |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study on Bayesian Spatial and Temporal Modeling Approach to Environmental Feature Inference Using Driving Signals From Vehicles |
| Sub Title (in English) | |
| Keyword(1) | connected vehicles |
| Keyword(2) | environmental sensing |
| Keyword(3) | spatial-temporal |
| Keyword(4) | Bayesian modeling |
| Keyword(5) | uncertain data |
| 1st Author's Name | Yukio Ogawa |
| 1st Author's Affiliation | Muroran Institute of Technology(Muroran-IT) |
| 2nd Author's Name | Go Hasegawa |
| 2nd Author's Affiliation | Tohoku University(Tohoku Univ.) |
| 3rd Author's Name | Masayuki Murata |
| 3rd Author's Affiliation | Osaka University(Osaka Univ.) |
| Date | 2022-03-11 |
| Paper # | IN2021-43 |
| Volume (vol) | vol.121 |
| Number (no) | IN-434 |
| Page | pp.pp.73-78(IN), |
| #Pages | 6 |
| Date of Issue | 2022-03-03 (IN) |